© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64462
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -heading
    -0.28
    ä»İ容
    -0.28
     vind
    -0.26
    缴åĪ°
    -0.25
    crow
    -0.25
    éģĵçIJĨ
    -0.25
    ä¿¡ç®±
    -0.24
    ä»İèĢĮ
    -0.24
    DirectoryName
    -0.24
    outside
    -0.24
    POSITIVE LOGITS
    weise
    0.27
     open
    0.27
     sweat
    0.26
     Open
    0.25
     fre
    0.24
    ^n
    0.24
    Open
    0.24
     #
    0.24
     khuyến
    0.24
     jav
    0.24
    Activations Density 1.475%

    No Known Activations